Llama (Meta) - Kyma API

Active model

Model ID	Parameters	Context	Speed	Best For
`llama-3.3-70b`	70B	128K	Fast	General, code, reasoning

Recommendation

Start with llama-3.3-70b — it’s the most popular open source model. Great at coding, reasoning, writing, and general tasks. Use gemini-2.5-flash or gemini-3-flash when you need very long context on Kyma.

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Hello!"}]
)

Model aliases

Alias	Resolves to
`balanced`	`llama-3.3-70b`

model="balanced"  # → llama-3.3-70b

Kimi (Moonshot)Gemma & Gemini (Google)

​Active model

​Recommendation

​Model aliases

Active model

Recommendation

Model aliases